Yi Wang (王毅) (original) (raw)

Biography

I am a Research Scientist at Shanghai AI Laboratory, led by Prof. Yu Qiao, Prof. Limin Wang, and Dr. Yali Wang. We are working on video understanding, foundation models, and related topics.

I did my Ph.D. at CSE of The Chinese University of Hong Kong, supervised by Prof. Jiaya Jia and Prof. Liwei Wang. My research interests include computer vision and deep learning, especially image generation and instance-level image understanding. Before that, I got the M.Sc. degree from Peking University (supervised by Prof. Yuexian Zou).

We are actively looking for motivated research fellows and interns with experience / interest in video processing / neural arch design / self-supervised learning / multimodal learning / dataset construction at Shanghai AI Laboratory. If you are interested in our video understanding project or other topics, please drop me an email.

• InternVideo: General Video Foundation Models via Generative and Discriminative Learning In Technical Report. 2022.
  Yi Wang*, Kunchang Li*, Yizhuo Li*, Yinan He*, Bingkun Huang*, Zhiyu Zhao*, Hongjie Zhang*, Jilan Xu, Yi Liu, Zun Wang, Sen Xing, Guo Chen, Junting Pan, Jiashuo Yu, Yali Wang*, Limin Wang*, Yu Qiao
  [Code] [Supp] [Presentation] [[Bib]]( @article{wang2022internvideo, title={InternVideo: General Video Foundation Models via Generative and Discriminative Learning}, author={Wang, Yi and Li, Kunchang and Li, Yizhuo and He, Yinan and Huang, Bingkun and Zhao, Zhiyu and Zhang, Hongjie and Xu, Jilan and Liu, Yi and Wang, Zun and Xing, Sen and Chen, Guo and Pan, Junting and Yu, Jiashuo and Wang, Yali and Wang, Limin and Qiao, Yu}, journal={arXiv preprint arXiv:2212.03191}, year={2022} })

• PalGAN: image colorization with palette generative adversarial networks In ECCV. 2022.
  Yi Wang, Menghan Xia, Lu Qi, Jing Shao, Yu Qiao
  [Code] [Presentation] [[Bib]]( @inproceedings{wang2022palgan, title={PalGAN: Image Colorization with Palette Generative Adversarial Networks}, author={Wang, Yi and Xia, Menghan and Qi, Lu and Shao, Jing and Qiao, Yu}, booktitle={ECCV}, year={2022} })

• MAT: Mask-aware transformer for large hole image inpainting In CVPR. 2022. [Best paper finalist & Oral]
  Wenbo Li, Zhe Lin, Kun Zhou, Lu Qi, Yi Wang#, Jiaya Jia
  [Code] [Presentation] [[Bib]]( @inproceedings{li2022mat, title={MAT: Mask-Aware Transformer for Large Hole Image Inpainting}, author={Li, Wenbo and Lin, Zhe and Zhou, Kun and Qi, Lu and Wang, Yi and Jia, Jiaya}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, year={2022} })

• Towards implicit text-guided 3D shape generation In CVPR. 2022.
  Zhengzhe Liu, Yi Wang, Xiaojuan Qi, Chi-Wing Fu
  [Code] [Supp] [Presentation] [[Bib]]( @InProceedings{Liu%5F2022%5FCVPR, author = {Liu, Zhengzhe and Wang, Yi and Qi, Xiaojuan and Fu, Chi-Wing}, title = {Towards Implicit Text-Guided 3D Shape Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition %28CVPR%29}, month = {June}, year = {2022}, pages = {17896-17906} })

• Image synthesis via semantic composition In ICCV. 2021.
  Yi Wang, Lu Qi, Ying-Cong Chen, Xiangyu Zhang, Jiaya Jia
  [Code] [Supp] [[Bib]]( @InProceedings{Wang%5F2021%5FICCV, author = {Wang, Yi and Qi, Lu and Chen, Ying-Cong and Zhang, Xiangyu and Jia, Jiaya}, title = {Image Synthesis via Semantic Composition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision %28ICCV%29}, month = {October}, year = {2021}, pages = {13749-13758} })

• Pointins: point-based instance segmentation In TPAMI. 2021.
  Lu Qi*, Yi Wang*, Yukang Chen, Ying-Cong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia
  [[Bib]](@article{qi2021pointins, title={Pointins: Point-based instance segmentation}, author={Qi, Lu and Wang, Yi and Chen, Yukang and Chen, Ying-Cong and Zhang, Xiangyu and Sun, Jian and Jia, Jiaya}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, year={2021}, publisher={IEEE} })

• Multi-scale aligned distillation for low-resolution detection In CVPR. 2021.
  Lu Qi*, Jason Kuen*, Jiuxiang Gu, Zhe Lin, Yi Wang, Yukang Chen, Yanwei Li, Jiaya Jia
  [Code] [[Bib]](@inproceedings{qi2021multi, title={Multi-scale Aligned Distillation for Low-Resolution Detection}, author={Qi, Lu and Kuen, Jason and Gu, Jiuxiang and Lin, Zhe and Wang, Yi and Chen, Yukang and Li, Yanwei and Jia, Jiaya}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={14443--14453}, year={2021} })

• VCNet: a robust approach to blind image inpainting In ECCV. 2020.
  Yi Wang, Ying-Cong Chen, Xin Tao, Jiaya Jia
  [Code] [Supp] [Slides] [Presentation] [[Bib]](@inproceedings{wang2020vcnet, title={VCNet: a robust approach to blind image inpainting}, author={Wang, Yi and Chen, Ying-Cong and Tao, Xin and Jia, Jiaya}, booktitle={ECCV}, pages={752--768}, year={2020}, organization={Springer} })

• Attentive normalization for conditional image generation In CVPR. 2020. [Oral]
  Yi Wang, Ying-Cong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia
  [Code] [Supp] [Slides] [Presentation] [[Bib]](@inproceedings{wang2020attentive, title={Attentive normalization for conditional image generation}, author={Wang, Yi and Chen, Ying-Cong and Zhang, Xiangyu and Sun, Jian and Jia, Jiaya}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={5094--5103}, year={2020} })

• Wide-context semantic image extrapolation In CVPR. 2019.
  Yi Wang, Xin Tao, Xiaoyong Shen, Jiaya Jia
  [Code] [Supp] [[Bib]](@inproceedings{wang2019wide, title={Wide-context semantic image extrapolation}, author={Wang, Yi and Tao, Xin and Shen, Xiaoyong and Jia, Jiaya}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={1399--1408}, year={2019} })

• Image inpainting via generative multi-column convolutional neural networks In NeurIPS. 2018.
  Yi Wang, Xin Tao, Xiaojuan Qi, Xiaoyong Shen, Jiaya Jia
  [Code] [Supp] [Poster] [[Bib]](@inproceedings{wang2018image, title={Image inpainting via generative multi-column convolutional neural networks}, author={Wang, Yi and Tao, Xin and Qi, Xiaojuan and Shen, Xiaoyong and Jia, Jiaya}, booktitle={Advances in Neural Information Processing Systems}, pages={331--340}, year={2018} })

• Manifold-based visual object counting In TIP. 2018.
  Yi Wang, Yuexian Zou, Wenwu Wang
  [Code] [[Bib]]( @article{wang2018manifold, title={Manifold-based visual object counting}, author={Wang, Yi and Zou, Yuexian and Wang, Wenwu}, journal={IEEE Transactions on Image Processing}, volume={27}, number={7}, pages={3248--3263}, year={2018}, publisher={IEEE} })

Academic Service

• Serve as a reviewer in multiple conferences / journals
  • Conference: CVPR, ECCV, ICCV, ICLR, NeurIPS, Siggraph Asia
  • Journals: TPAMI, IJCV, TIP, CVIU, TMM, TCP

Awards & Honors

• Champions of FHP, NLQ, STOIA, SCOD, and MQ Challenges@ECCV Ego4D Workshop, 2022 [Technical Report] [Code] [Slide]
• Champion of Room-Across-Room Habitat VLN Challenge@CVPR Embodied AI Workshop, 2022 [Technical Report] [Code]
• Champions of REVERIE VLN Challenges in CSIG, 2022 [Technical Report]
• Champion of 2nd COVID-19 Competition@ECCV AIMIA workshop, 2022 [Technical Report]
• Postgraduate Studentship in CUHK, 2017-2021
• Beijing/PKU Outstanding Graduate Award, 2017
• PKU Outstanding Master Thesis Award, 2017
• National Scholarship, 2011/2015/2016
• Northwest A&F University Outstanding Graduate Award, 2014
• Northwest A&F University Outstanding Bachelor Thesis Award, 2014
• President Scholarship at Northwest A&F University, 2012